← Search

Michael McCabe

9 accepted papers

2026

Overtone: Cyclic Patch Modulation for Cleaner, Faster Physics Emulators

ICLR 2026poster

Transformer-based PDE surrogates achieve remarkable performance but face two key challenges: fixed patch sizes cause systematic error accumulation at harmonic frequencies, and computational costs remain inflexible regardless of problem complexity or available resources. We introduce Overtone, a unif…

Cited by 0SourcecodeScholar
2026

Walrus: A Cross-domain Foundation Model for Continuum Dynamics

ICML 2026spotlight

Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unstable long-term dynamics inhibit learning from sufficiently diverse dynamics, while varying resolutions and dimensionalit…

Cited by 0SourceScholar
2025

AION-1: Omnimodal Foundation Model for Astronomical Sciences

NeurIPS 2025poster

While foundation models have shown promise across a variety of fields, astronomy lacks a unified framework for joint modeling across its highly diverse data modalities. In this paper, we present AION-1, the first large-scale multimodal foundation family of models for astronomy. AION-1 enables arbitr…

Cited by 0SourceScholar
2025

Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation

NeurIPS 2025poster

The steep computational cost of diffusion models at inference hinders their use as fast physics emulators. In the context of image and video generation, this computational drawback has been addressed by generating in the latent space of an autoencoder instead of the pixel space. In this work, we inv…

Cited by 0SourcecodeScholar
2025

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

NeurIPS 2025poster

Conditional diffusion models provide a natural framework for probabilistic prediction of dynamical systems and have been successfully applied to fluid dynamics and weather prediction. However, in many settings, the available information at a given time represents only a small fraction of what is nee…

Cited by 0SourceScholar
2025

SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and Segmentation

NeurIPS 2025poster

The global rise in wildfire frequency and intensity over the past decade underscores the need for improved fire monitoring techniques. To advance deep learning research on wildfire detection and its associated human health impacts, we introduce **SmokeViz**, a large-scale machine learning dataset of…

Cited by 1SourceScholar
2024

Multiple Physics Pretraining for Spatiotemporal Surrogate Models

NeurIPS 2024poster

We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling of spatiotemporal systems with transformers. In MPP, rather than training one model on a specific physical system, we train a backbone model to predict the dynamics o…

Cited by 3SourcePDFScholar
2024

The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

NeurIPS 2024poster

Machine learning based surrogate models offer researchers powerful tools for accelerating simulation-based workflows. However, as standard datasets in this space often cover small classes of physical behavior, it can be difficult to evaluate the efficacy of new approaches. To address this gap, we in…